sharepoint-mcp: Skill for Claude Code

.agents/skills/code-reviewer/SKILL.md

code-reviewer is a skill for Claude Code, Codex from ravikant1918/sharepoint-mcp. It costs 32 tokens per session (882 once invoked), scanned A, original, MIT.

A code-audit skill that reviews software for architecture, scalability, security, performance, production readiness, and documentation quality.

In plain words
What is it for?
Use it for structured reviews of code, architecture, async operations, database access, retries, dependencies, documentation, and CI/CD checks.
Why use it?
It helps uncover design problems, security risks, inefficient code, and maintainability issues before they reach production.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is ravikant1918/sharepoint-mcp's own configuration. It tells Claude Code and Codex how to work on sharepoint-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sharepoint-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ravikant1918/sharepoint-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ravikant1918/sharepoint-mcp/main/.agents/skills/code-reviewer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ravikant1918/sharepoint-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ravikant1918/sharepoint-mcp/code-reviewer.svg)](https://agentmods.dev/skills/ravikant1918/sharepoint-mcp/code-reviewer)
Your own site
<a href="https://agentmods.dev/skills/ravikant1918/sharepoint-mcp/code-reviewer"><img src="https://agentmods.dev/badge/skills/ravikant1918/sharepoint-mcp/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 882 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00882
Opus 5 $0.00016 $0.00441
Sonnet 5 $0.00006 $0.00176
Haiku 4.5 $0.00003 $0.00088

Measured 8d ago against content hash f4b2239cc953, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

code-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/code-reviewer/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer Skill

This skill is used inside an enterprise-grade MCP server.

━━━━━━━━━━━━━━━━━━━━━━ PRIMARY OBJECTIVE ━━━━━━━━━━━━━━━━━━━━━━

The "code-reviewer" skill must perform deep, production-level code audits and enforce:

• High scalability • Enterprise-grade architecture • Production readiness • Security best practices • Performance optimization • Clean documentation standards • Strict Markdown quality rules

The output must be structured, deterministic, and suitable for CI/CD automation.

━━━━━━━━━━━━━━━━━━━━━━ CORE RESPONSIBILITIES ━━━━━━━━━━━━━━━━━━━━━━

1️⃣ Code Quality & Architecture

  • Detect code smells (God objects, tight coupling, duplication, long functions)
  • Enforce SOLID principles
  • Identify anti-patterns
  • Suggest modularization opportunities
  • Validate separation of concerns
  • Ensure dependency injection patterns when applicable
  • Recommend layered architecture (API → Service → Core → Infra)

2️⃣ Scalability & Production Readiness

  • Identify blocking I/O in async contexts
  • Detect inefficient loops or N+1 patterns
  • Suggest caching strategies
  • Validate retry/backoff logic
  • Recommend idempotency where needed
  • Detect race conditions
  • Ensure structured logging is used
  • Validate observability hooks (metrics/logging readiness)

3️⃣ Security Review

  • Validate input sanitization
  • Check authentication & authorization flow
  • Detect hardcoded secrets
  • Validate environment variable usage
  • Detect injection vulnerabilities
  • Check rate limiting protections
  • Ensure secure error handling (no sensitive leakage)

4️⃣ Performance Optimization

  • Identify unnecessary allocations
  • Suggest lazy loading where applicable
  • Flag heavy operations inside loops
  • Recommend async usage where applicable
  • Identify potential memory leaks
  • Detect excessive network calls

5️⃣ Documentation Standards Enforce:

• Proper docstrings for all public functions/classes • Type hints required • Clear parameter descriptions • Return type documentation • Exceptions documented • Usage examples for exported APIs

Docstring style must follow:

  • Google style (preferred) OR
  • NumPy style (if Python)
  • JSDoc (if TypeScript/JS)

6️⃣ Markdown & Repository Standards For README and docs:

  • Proper heading hierarchy (H1 → H2 → H3)
  • No skipped heading levels
  • Code blocks must specify language
  • Installation section required
  • Usage examples required
  • Architecture section required
  • Production considerations required
  • Clear table of contents if > 500 lines
  • No broken links
  • Consistent formatting
  • No trailing spaces
  • No inconsistent bullet indentation

━━━━━━━━━━━━━━━━━━━━━━ OUTPUT FORMAT (STRICT) ━━━━━━━━━━━━━━━━━━━━━━

Return output in this structure:

Read the full file on GitHub · 179 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 179 lines · 32 tokens per session scan A f4b2239cc953

Subscribe to this mod's changes

code-reviewer is a skill published in the GitHub repository ravikant1918/sharepoint-mcp (12 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 882 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.